Stealing Reasoning Traces from Proprietary LLM APIs — Ilia Shumailov & Alexander Panfilov

0:00-49:00

Tim Scarfe speaks with Ilia Shumailov and Alexander Panfilov about their paper, Stealing Reasoning Traces from Proprietary LLM APIs.The core bug sounds deceptively simple: providers return encrypted reasoning state so conversations can be resumed or forked. But those blobs can be replayed across users and sibling models. A smaller model can ask the provider to decrypt the trace, then repeat the hidden reasoning in plain text. The discussion covers leaked private data, a broadly reusable jailbreak, poisoned agent traces, chain-of-thought monitoring, responsible disclosure, and possible defenses. Ilia Shumailov is an AI and security researcher, formerly at Google DeepMind, who completed his Cambridge PhD under Ross Anderson. Alexander Panfilov is a PhD researcher at the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems, working on AI safety, adversarial machine learning, and LLM red-teaming.

Publisher

Machine Learning Street Talk (MLST)

Link

podcasters.spotify.com/pod/show/machinelearningstreettalk/episodes/Stealing-Reasoning-Traces-from-Proprietary-LLM-APIs--Ilia-Shumailov--Alexander-Panfilov-e3nonlk

Published

August 22, 2026

Duration

49 min

Format

Podcast

Category

Issues · Tech News

Source

RSS feed

ML

Machine Learning Street Talk (MLST)

@mlstreettalk

#stealingreasoningtraces #proprietaryllmapis #alexanderpanfilov

The Nile